Online Learning with Improving Agents: Multiclass, Budgeted Agents and Bandit Learners
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918345017655296 |
|---|---|
| author | Ashkezari, Sajad Ben-David, Shai |
| author_facet | Ashkezari, Sajad Ben-David, Shai |
| contents | We investigate the recently introduced model of learning with improvements, where agents are allowed to make small changes to their feature values to be warranted a more desirable label. We extensively extend previously published results by providing combinatorial dimensions that characterize online learnability in this model, by analyzing the multiclass setup, learnability in a bandit feedback setup, modeling agents' cost for making improvements and more. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17103 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Online Learning with Improving Agents: Multiclass, Budgeted Agents and Bandit Learners Ashkezari, Sajad Ben-David, Shai Machine Learning We investigate the recently introduced model of learning with improvements, where agents are allowed to make small changes to their feature values to be warranted a more desirable label. We extensively extend previously published results by providing combinatorial dimensions that characterize online learnability in this model, by analyzing the multiclass setup, learnability in a bandit feedback setup, modeling agents' cost for making improvements and more. |
| title | Online Learning with Improving Agents: Multiclass, Budgeted Agents and Bandit Learners |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.17103 |